python类getdecoder()的实例源码

def uppercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\U[0-9a-fA-F]{8}',
        lambda m: unicode_escape(m.group(0))[0],
        s)

def lowercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\u[0-9a-fA-F]{4}',
        lambda m: unicode_escape(m.group(0))[0],
        s)

def uppercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\U[0-9a-fA-F]{8}',
        lambda m: unicode_escape(m.group(0))[0],
        s)

def lowercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\u[0-9a-fA-F]{4}',
        lambda m: unicode_escape(m.group(0))[0],
        s)

def test_decode_callback(self):
        codecs.register_error("UnicodeInternalTest", codecs.ignore_errors)
        decoder = codecs.getdecoder("unicode_internal")
        with support.check_warnings(('unicode_internal codec has been '
                                     'deprecated', DeprecationWarning)):
            ab = "ab".encode("unicode_internal").decode()
            ignored = decoder(bytes("%s\x22\x22\x22\x22%s" % (ab[:4], ab[4:]),
                                    "ascii"),
                              "UnicodeInternalTest")
        self.assertEqual(("ab", 12), ignored)

def test_getdecoder(self):
        self.assertRaises(TypeError, codecs.getdecoder)
        self.assertRaises(LookupError, codecs.getdecoder, "__spam__")

def test_bad_decode_args(self):
        for encoding in all_unicode_encodings:
            decoder = codecs.getdecoder(encoding)
            self.assertRaises(TypeError, decoder)
            if encoding not in ("idna", "punycode"):
                self.assertRaises(TypeError, decoder, 42)

def test_basics(self):
        binput = bytes(range(256))
        for encoding in bytes_transform_encodings:
            # generic codecs interface
            (o, size) = codecs.getencoder(encoding)(binput)
            self.assertEqual(size, len(binput))
            (i, size) = codecs.getdecoder(encoding)(o)
            self.assertEqual(size, len(o))
            self.assertEqual(i, binput)

def test_errorcallback_longindex(self):
        dec = codecs.getdecoder('euc-kr')
        myreplace  = lambda exc: ('', sys.maxsize+1)
        codecs.register_error('test.cjktest', myreplace)
        self.assertRaises(IndexError, dec,
                          b'apple\x92ham\x93spam', 'test.cjktest')

def _unescape(text):
    """Unescape unicode character codes within a string.
    """
    pattern = r'\\{1,2}u[0-9a-fA-F]{4}'
    decode = lambda x: codecs.getdecoder('unicode_escape')(x.group())[0]
    return re.sub(pattern, decode, text)

def codepage(self, codepage):
        if not isinstance(codepage, CodePage):
            raise TypeError("codepage should be a CodePage, not a %r" % type(codepage))
        meta = self._meta
        if meta.status != READ_WRITE:
            raise DbfError('%s not in read/write mode, unable to change codepage' % meta.filename)
        meta.header.codepage(codepage.code)
        meta.decoder = codecs.getdecoder(codepage.name)
        meta.encoder = codecs.getencoder(codepage.name)
        self._update_disk(headeronly=True)

def codepage(self, codepage):
        if not isinstance(codepage, CodePage):
            raise TypeError("codepage should be a CodePage, not a %r" % type(codepage))
        meta = self._meta
        if meta.status != READ_WRITE:
            raise DbfError('%s not in read/write mode, unable to change codepage' % meta.filename)
        meta.header.codepage(codepage.code)
        meta.decoder = codecs.getdecoder(codepage.name)
        meta.encoder = codecs.getencoder(codepage.name)
        self._update_disk(headeronly=True)

def codepage(self, codepage):
        if not isinstance(codepage, CodePage):
            raise TypeError("codepage should be a CodePage, not a %r" % type(codepage))
        meta = self._meta
        if meta.status != READ_WRITE:
            raise DbfError('%s not in read/write mode, unable to change codepage' % meta.filename)
        meta.header.codepage(codepage.code)
        meta.decoder = codecs.getdecoder(codepage.name)
        meta.encoder = codecs.getencoder(codepage.name)
        self._update_disk(headeronly=True)

def test_nonascii_text_cptrans(self):
        "check non-ascii text to unicode"
        table = Table(':memory:', 'data C(50); memo M', codepage='cp437', dbf_type='vfp', on_disk=False)
        table.open()
        decoder = codecs.getdecoder('cp437')
        if py_ver < (3, 0):
            high_ascii = decoder(''.join(chr(c) for c in range(128, 128+50)))[0]
        else:
            high_ascii = bytes(range(128, 128+50)).decode('cp437')
        table.append(dict(data=high_ascii, memo=high_ascii))
        self.assertEqual(table[0].data, high_ascii)
        self.assertEqual(table[0].memo, high_ascii)
        table.close()

def uppercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\U[0-9a-fA-F]{8}',
        lambda m: unicode_escape(m.group(0))[0],
        s)

def lowercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\u[0-9a-fA-F]{4}',
        lambda m: unicode_escape(m.group(0))[0],
        s)

def _unescape(text):
    """Unescape unicode character codes within a string.
    """
    pattern = r'\\{1,2}u[0-9a-fA-F]{4}'
    decode = lambda x: codecs.getdecoder('unicode_escape')(x.group())[0]
    return re.sub(pattern, decode, text)

def test_decode_callback(self):
        if sys.maxunicode > 0xffff:
            codecs.register_error("UnicodeInternalTest", codecs.ignore_errors)
            decoder = codecs.getdecoder("unicode_internal")
            ab = u"ab".encode("unicode_internal")
            ignored = decoder("%s\x22\x22\x22\x22%s" % (ab[:4], ab[4:]),
                "UnicodeInternalTest")
            self.assertEqual((u"ab", 12), ignored)

def test_getdecoder(self):
        self.assertRaises(TypeError, codecs.getdecoder)
        self.assertRaises(LookupError, codecs.getdecoder, "__spam__")